Automatic Fusion of Similar Sentences in Portuguese

Abstract

This paper presents a Portuguese sentence fusion model. Sentence fusion is a text-to-text generation task which takes a set of similar sentences as input and combines these into a single output sentence. This process is of extreme relevance in many NLP applications, for instance, to treat redundancies in Multidocument Summarization by fusing information from a set of related sentences into a new one. We present three intrinsic evaluations of the model and the results obtained suggest that it has potential.